🧠 Reasoning Ecosystem
This skill is the entry point of its ecosystem. It chooses a workflow, checks which member skills are installed, runs them in order with explicit handoffs, and degrades gracefully when a member is missing. The workflow map lives in references/workflows.json; the handoff format lives in references/handoff-contract.md.
Catalog
Domain: Reasoning, Planning Gates & Prompting — Clarify intent, stress-test plans, compare perspectives, and craft prompts, without stacking redundant question gates.
Philosophy: Ask only what changes the outcome. Run at most one clarification gate per request, in a fixed precedence, then act. Use multiple perspectives when trade-offs are real, not by default.
| Skill |
Role |
Handoff artifact |
@project-focus-first |
Hard gate: fixes one primary focus before a new project is discussed. |
inline handoff block |
@ask-first-act-later |
Consultant mode: asks targeted questions before any implementation. |
inline handoff block |
@assumption-checker |
Surfaces and verifies technical, data, business, and intent assumptions. |
inline handoff block |
@plan-hardener |
Stress-tests plans with assumption-first review modes. |
inline handoff block |
@multi-brain |
Synthesizes three perspectives into one consensus answer. |
inline handoff block |
@multi-brain-experts |
Selects three domain experts for the perspectives. |
inline handoff block |
@multi-brain-debate |
Runs a two-round adversarial debate before a verdict. |
inline handoff block |
@multi-brain-score |
Adds confidence scores and weighted consensus. |
inline handoff block |
@prompt-crafter |
Designs, optimizes, and evaluates prompts and agent specs. |
inline handoff block |
@turkish-prompt-compiler |
Measures and compresses long Turkish prompts without losing intent. |
inline handoff block |
Router Protocol
Follow this protocol whenever this ecosystem is invoked.
- Match. Compare the request with each workflow's When phrases. Pick one workflow, or route straight to a single member skill when the request is narrow. If two workflows fit equally, ask one question to choose. If the request belongs to another domain, use the ecosystem index in
@ecosystem-orchestration.
- Preflight. Find out which step skills are installed: check the skills your host lists, or run
python <skill-dir>/scripts/install_all.py --status --workflow <id> (<skill-dir> is the folder containing this SKILL.md). Show a short plan: step, skill, installed or missing, condition, expected artifact.
- Missing skills never block. Offer once: (a) install them —
install_all.py --workflow <id> prints the commands and only runs them with --execute after the user agrees; or (b) continue in fallback mode — perform the step yourself using its Does and Done when columns and label that output fallback.
- Conditions. Skip optional steps whose condition does not hold, and say which steps you skipped and why.
- Execute. Run steps in order. Steps that share a parallel group are independent and may run concurrently (
@parallel-planner). Pass artifacts as described in references/handoff-contract.md. Check each step's Done when before moving on.
- Gates. Before any destructive, irreversible, or production-impacting action, stop at
@checkpoint-guardian, or ask for explicit confirmation when it is not installed.
- Failures. When a step misses its Done when, hand off to
@error-recovery. Without it, retry once with a changed approach, then report the blocker with evidence instead of guessing.
- State. Keep a run log (workflow id, step, status, artifact). Record it with
@memory-ledger when installed, and write a @session-transfer handoff if the run will continue in another session.
- Finish. Summarize artifacts, skipped steps, open risks, and the most relevant next workflow.
Skip this protocol when the user names one specific skill (invoke it directly) or asks a quick factual question that needs no workflow.
Workflows
1. Clarification Gate Flow (reason-clarify)
When: “new project idea”; “ambiguous request”; “ask me before you build”
| # |
Skill |
Does |
Done when |
Condition |
Parallel group |
| 1 |
@project-focus-first (optional) |
Establish the primary focus for a brand-new project. |
User chose one primary focus. |
New project and no focus stated |
— |
| 2 |
@ask-first-act-later (optional) |
Ask the few questions that change the outcome. |
Requirements are confirmed by the user. |
User explicitly asked to be consulted first |
— |
| 3 |
@assumption-checker |
List remaining assumptions and verify the risky ones. |
No unverified high-risk assumption remains. |
— |
— |
2. Decision Quality Flow (reason-decision)
When: “which option is better”; “debate these approaches”; “give me a robust recommendation”
| # |
Skill |
Does |
Done when |
Condition |
Parallel group |
| 1 |
@multi-brain |
Produce three perspectives and a consensus. |
Consensus names the chosen option and why. |
— |
— |
| 2 |
@multi-brain-experts (optional) |
Swap generic perspectives for domain experts. |
Three relevant experts were selected. |
Domain expertise matters (security, cost, UX) |
— |
| 3 |
@multi-brain-debate (optional) |
Stress the top two options through rebuttals. |
Verdict addresses every rebuttal. |
Two strong options clash |
— |
| 4 |
@multi-brain-score (optional) |
Weight the consensus by stated confidence. |
Low-confidence areas are flagged. |
— |
— |
| 5 |
@output-critic (optional) |
Score the final recommendation before delivery. |
Recommendation meets the acceptance threshold. |
— |
— |
3. Plan Hardening Flow (reason-plan-review)
When: “review my plan”; “find risks in this architecture”; “red-team this plan”
| # |
Skill |
Does |
Done when |
Condition |
Parallel group |
| 1 |
@plan-hardener |
Pick the review mode by size and risk and run it. |
Every critical risk has a mitigation or an owner. |
— |
— |
| 2 |
@task-decomposer (optional) |
Turn the hardened plan into executable subtasks. |
Subtasks carry the mitigations. |
— |
— |
4. Prompt Engineering Flow (reason-prompting)
When: “write a system prompt”; “optimize this prompt”; “compress this Turkish prompt”
| # |
Skill |
Does |
Done when |
Condition |
Parallel group |
| 1 |
@prompt-crafter |
Design or optimize the prompt with an explicit output contract. |
Prompt passes the final check list. |
— |
— |
| 2 |
@turkish-prompt-compiler (optional) |
Measure and compress a long Turkish prompt. |
Savings reported with fidelity preserved. |
Prompt is long and in Turkish |
— |
Direct handoffs
@project-focus-first → @b2b-founder-roadmap: The chosen focus is B2B go-to-market.
@prompt-crafter → @ugc-crafter: The prompt targets UGC-style image or video generation.
@prompt-crafter → @jev-orchestrator: The prompt only returns a small fixed label set.
Gate precedence
Run at most one clarification gate per request, choosing the first one whose condition holds. A gate that another gate already satisfied must be skipped. @checkpoint-guardian is not a clarification gate; it always applies before irreversible actions.
@project-focus-first — A brand-new project with no stated primary focus.
@ask-first-act-later — The user explicitly asked for questions before action.
@assumption-checker — A multi-step or ambiguous task is about to start.
@plan-hardener — A written plan exists and must be stress-tested.
1---2name: ecosystem-reasoning3description: "Route clarification, plan review, multi-perspective decisions, and prompt engineering through the right fth-skills reasoning skills, with a fixed precedence so question gates never stack. Use when the user wants options compared or debated, a plan stress-tested, requirements clarified before building, or a prompt designed or optimized."4metadata:5 source: https://skillmd.com/skills/fatih-developer/ecosystem-reasoning6---78# 🧠 Reasoning Ecosystem910This skill is the entry point of its ecosystem. It chooses a workflow, checks which member skills are installed, runs them in order with explicit handoffs, and degrades gracefully when a member is missing. The workflow map lives in `references/workflows.json`; the handoff format lives in `references/handoff-contract.md`.1112## Catalog1314<!-- BEGIN GENERATED: ecosystem-catalog (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->15**Domain:** Reasoning, Planning Gates & Prompting — Clarify intent, stress-test plans, compare perspectives, and craft prompts, without stacking redundant question gates.1617**Philosophy:** Ask only what changes the outcome. Run at most one clarification gate per request, in a fixed precedence, then act. Use multiple perspectives when trade-offs are real, not by default.1819| Skill | Role | Handoff artifact |20|---|---|---|21| `@project-focus-first` | Hard gate: fixes one primary focus before a new project is discussed. | inline handoff block |22| `@ask-first-act-later` | Consultant mode: asks targeted questions before any implementation. | inline handoff block |23| `@assumption-checker` | Surfaces and verifies technical, data, business, and intent assumptions. | inline handoff block |24| `@plan-hardener` | Stress-tests plans with assumption-first review modes. | inline handoff block |25| `@multi-brain` | Synthesizes three perspectives into one consensus answer. | inline handoff block |26| `@multi-brain-experts` | Selects three domain experts for the perspectives. | inline handoff block |27| `@multi-brain-debate` | Runs a two-round adversarial debate before a verdict. | inline handoff block |28| `@multi-brain-score` | Adds confidence scores and weighted consensus. | inline handoff block |29| `@prompt-crafter` | Designs, optimizes, and evaluates prompts and agent specs. | inline handoff block |30| `@turkish-prompt-compiler` | Measures and compresses long Turkish prompts without losing intent. | inline handoff block |31<!-- END GENERATED: ecosystem-catalog -->3233## Router Protocol3435<!-- BEGIN GENERATED: ecosystem-router (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->36Follow this protocol whenever this ecosystem is invoked.37381. **Match.** Compare the request with each workflow's *When* phrases. Pick one workflow, or route straight to a single member skill when the request is narrow. If two workflows fit equally, ask one question to choose. If the request belongs to another domain, use the ecosystem index in `@ecosystem-orchestration`.392. **Preflight.** Find out which step skills are installed: check the skills your host lists, or run `python <skill-dir>/scripts/install_all.py --status --workflow <id>` (`<skill-dir>` is the folder containing this `SKILL.md`). Show a short plan: step, skill, installed or missing, condition, expected artifact.403. **Missing skills never block.** Offer once: (a) install them — `install_all.py --workflow <id>` prints the commands and only runs them with `--execute` after the user agrees; or (b) continue in fallback mode — perform the step yourself using its *Does* and *Done when* columns and label that output `fallback`.414. **Conditions.** Skip optional steps whose condition does not hold, and say which steps you skipped and why.425. **Execute.** Run steps in order. Steps that share a parallel group are independent and may run concurrently (`@parallel-planner`). Pass artifacts as described in `references/handoff-contract.md`. Check each step's *Done when* before moving on.436. **Gates.** Before any destructive, irreversible, or production-impacting action, stop at `@checkpoint-guardian`, or ask for explicit confirmation when it is not installed.447. **Failures.** When a step misses its *Done when*, hand off to `@error-recovery`. Without it, retry once with a changed approach, then report the blocker with evidence instead of guessing.458. **State.** Keep a run log (workflow id, step, status, artifact). Record it with `@memory-ledger` when installed, and write a `@session-transfer` handoff if the run will continue in another session.469. **Finish.** Summarize artifacts, skipped steps, open risks, and the most relevant next workflow.4748**Skip this protocol** when the user names one specific skill (invoke it directly) or asks a quick factual question that needs no workflow.49<!-- END GENERATED: ecosystem-router -->5051## Workflows5253<!-- BEGIN GENERATED: ecosystem-workflows (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->54### 1. Clarification Gate Flow (`reason-clarify`)5556**When:** “new project idea”; “ambiguous request”; “ask me before you build”5758| # | Skill | Does | Done when | Condition | Parallel group |59|---|---|---|---|---|---|60| 1 | `@project-focus-first` *(optional)* | Establish the primary focus for a brand-new project. | User chose one primary focus. | New project and no focus stated | — |61| 2 | `@ask-first-act-later` *(optional)* | Ask the few questions that change the outcome. | Requirements are confirmed by the user. | User explicitly asked to be consulted first | — |62| 3 | `@assumption-checker` | List remaining assumptions and verify the risky ones. | No unverified high-risk assumption remains. | — | — |6364### 2. Decision Quality Flow (`reason-decision`)6566**When:** “which option is better”; “debate these approaches”; “give me a robust recommendation”6768| # | Skill | Does | Done when | Condition | Parallel group |69|---|---|---|---|---|---|70| 1 | `@multi-brain` | Produce three perspectives and a consensus. | Consensus names the chosen option and why. | — | — |71| 2 | `@multi-brain-experts` *(optional)* | Swap generic perspectives for domain experts. | Three relevant experts were selected. | Domain expertise matters (security, cost, UX) | — |72| 3 | `@multi-brain-debate` *(optional)* | Stress the top two options through rebuttals. | Verdict addresses every rebuttal. | Two strong options clash | — |73| 4 | `@multi-brain-score` *(optional)* | Weight the consensus by stated confidence. | Low-confidence areas are flagged. | — | — |74| 5 | `@output-critic` *(optional)* | Score the final recommendation before delivery. | Recommendation meets the acceptance threshold. | — | — |7576### 3. Plan Hardening Flow (`reason-plan-review`)7778**When:** “review my plan”; “find risks in this architecture”; “red-team this plan”7980| # | Skill | Does | Done when | Condition | Parallel group |81|---|---|---|---|---|---|82| 1 | `@plan-hardener` | Pick the review mode by size and risk and run it. | Every critical risk has a mitigation or an owner. | — | — |83| 2 | `@task-decomposer` *(optional)* | Turn the hardened plan into executable subtasks. | Subtasks carry the mitigations. | — | — |8485### 4. Prompt Engineering Flow (`reason-prompting`)8687**When:** “write a system prompt”; “optimize this prompt”; “compress this Turkish prompt”8889| # | Skill | Does | Done when | Condition | Parallel group |90|---|---|---|---|---|---|91| 1 | `@prompt-crafter` | Design or optimize the prompt with an explicit output contract. | Prompt passes the final check list. | — | — |92| 2 | `@turkish-prompt-compiler` *(optional)* | Measure and compress a long Turkish prompt. | Savings reported with fidelity preserved. | Prompt is long and in Turkish | — |9394### Direct handoffs9596- `@project-focus-first` → `@b2b-founder-roadmap`: The chosen focus is B2B go-to-market.97- `@prompt-crafter` → `@ugc-crafter`: The prompt targets UGC-style image or video generation.98- `@prompt-crafter` → `@jev-orchestrator`: The prompt only returns a small fixed label set.99100### Gate precedence101102Run **at most one** clarification gate per request, choosing the first one whose condition holds. A gate that another gate already satisfied must be skipped. `@checkpoint-guardian` is not a clarification gate; it always applies before irreversible actions.1031041. `@project-focus-first` — A brand-new project with no stated primary focus.1052. `@ask-first-act-later` — The user explicitly asked for questions before action.1063. `@assumption-checker` — A multi-step or ambiguous task is about to start.1074. `@plan-hardener` — A written plan exists and must be stress-tested.108<!-- END GENERATED: ecosystem-workflows -->